COIOSDeep risk insights through multi-disciplinary research across the globe
trees beside white and brown house during daytime
Item confirms Peer-reviewed Added

Machine learning model predicted deaths best in diabetes with hypertension

Among 2,428 US adults with type 2 diabetes and hypertension in NHANES, a random forest predicted death with an AUC of 0.873, against 0.783 for logistic regression.

NHANES 1999 to 2018, linked to death records to 2019, supplied 2,428 US adults with both type 2 diabetes and hypertension, of whom 719 died. The authors tested five ways of predicting death, and the random forest reached an AUC of 0.873 against 0.783 for logistic regression. Age, race, chronic kidney disease, BMI and blood urea nitrogen were the leading predictors.

Why it is interesting: The gain over standard logistic regression rests on a single national survey sample.

Source
JMIR Medical Informatics, 22 September 2026
Paper
Development and Validation of a Machine Learning-Based Model for Predicting All-Cause Mortality Risk in Patients With Type 2 Diabetes Mellitus Combined With Hypertension: National Cohort Study
Authors
Ding W, Fang L, Fang C
DOI
10.2196/85557
Type
Peer-reviewed article
Design
Prediction model development on NHANES 1999-2018 linked to deaths to 2019; n=2428 adults with type 2 diabetes and hypertension, 719 deaths, median follow-up 6.75 years
Verdict
Confirms prior evidence
Driver
AI in medicine
Driver
Obesity, diabetes and GLP-1
Free full text
Free to read at the publisher
Abstract — the authors' own words, CC BY

Background

Type 2 diabetes mellitus (T2DM) combined with hypertension significantly increases mortality risk, yet accurate risk prediction models remain limited. Objective

We aimed to develop and validate machine learning-based models to predict all-cause mortality in patients with T2DM and hypertension. Methods

We analyzed data from the National Health and Nutrition Examination Survey from 1999 to 2018 linked with mortality data up to December 31, 2019. Adult participants (aged ≥20 years) with concurrent T2DM and hypertension were included. Five machine learning algorithms were developed and compared: random forest, light gradient boosting machine, decision tree, extreme gradient boosting, and logistic regression. Model performance was evaluated using area under the curve (AUC), calibration plots, and decision curve analysis. Results

A total of 2428 participants were included (mean age 62.05, SE 0.33 years; n=1218, 50.15% female). During a median follow-up of 6.75 (IQR 4.20-8.90) years, among the 2428 patients, 719 (29.6%) deaths occurred. The random forest model demonstrated superior performance (AUC=0.873, 95% CI 0.856-0.891) compared to light gradient boosting machine (AUC=0.785), decision tree (AUC=0.732), extreme gradient boosting (AUC=0.792), and logistic regression (AUC=0.783). Key predictive features included age, race, chronic kidney disease, BMI, and blood urea nitrogen. The model exhibited excellent calibration and clinical utility across various risk thresholds. Conclusions

Our machine learning-based model provides accurate all-cause mortality prediction for patients with T2DM and hypertension, potentially supporting clinical decision-making and risk stratification in this high-risk population.

Other drivers in Data, models and systems